The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using python <aegis-workspace-helper> to perform workspace initialization, indexing, and health checks. These commands represent direct interactions with the system environment. The skill also checks for configuration settings in ~/.config/aegis/config.toml to determine its activation mode.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes external requirement documents and design specifications to generate implementation plans and tasks.\n
Ingestion points: Requirements, Spec Briefs, and Design Specs are identified as primary inputs in SKILL.md.\n
Boundary markers: The skill uses a Requirement Ready Check and an Execution Handoff protocol with user confirmation flags to manage transitions between planning and execution.\n
Capability inventory: The agent has the capability to write implementation plans to the filesystem and execute shell-based workspace management tools.\n
Sanitization: No explicit sanitization or filtering of the input text from external requirements is performed before task generation.

writing-plans